© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 89591
    Prev
    Next
    INDEX
    Explanations

    buy/purchase/transaction

    np_acts-logits-general · gemini-2.5-flash-lite

    protect, directory, since, compile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    玩意
    0.41
    郎
    0.39
    leistung
    0.39
    stw
    0.38
     consist
    0.38
     recuperar
    0.38
     mechanism
    0.37
     shorter
    0.37
    ৩০
    0.37
    lickr
    0.37
    POSITIVE LOGITS
     एंट
    0.55
    🚪
    0.52
    🖌
    0.52
     epistemology
    0.51
    🍶
    0.51
    ⛸
    0.51
     anisotropic
    0.49
    ⏹
    0.48
    🥓
    0.47
    าส
    0.47
    Activations Density 0.000%

    No Known Activations